AI

Data that Speaks for Itself

Data that Speaks for Itself

DALL·E 3 and Midjourney Fail Astral Codex Ten's Image Generation Bet

DALL·E 3 and Midjourney Fail Astral Codex Ten's Image Generation Bet

How RLHF Shifts LLMs from Autocompletion to Conversational Understanding

How RLHF Shifts LLMs from Autocompletion to Conversational Understanding

2022 Blog Recap: Trends in AI, Language, & Data

2022 Blog Recap: Trends in AI, Language, & Data

Evaluating Generative AI: Did Astral Codex Ten Win His Bet on AI Progress?

Evaluating Generative AI: Did Astral Codex Ten Win His Bet on AI Progress?

30% of Google's Emotions Dataset is Mislabeled

30% of Google's Emotions Dataset is Mislabeled

Humans vs. Gary Marcus vs. Slate Star Codex: When is an AI failure actually a failure?

Humans vs. Gary Marcus vs. Slate Star Codex: When is an AI failure actually a failure?

How Surge AI Built OpenAI's GSM8K Dataset of 8,500 Math Problems

How Surge AI Built OpenAI's GSM8K Dataset of 8,500 Math Problems

We asked 100 humans to draw the DALL·E prompts

We asked 100 humans to draw the DALL·E prompts